Skip to main content
Glama

record_baseline

Snapshot a known-good containerlab topology as Netdryrun BGP checks, pinning sessions, prefix counts and routes so you can dry-run later config changes against a baseline.

Instructions

Snapshot a known-good lab (containerlab topology file) as netdryrun.yml check text: every established BGP session, prefix count (today's count as min, max with 20% headroom; on each eBGP neighbor, only the prefixes it sends today, or an exact count where the driver can't list them) and BGP route. Call it when no checks exist, before changing the configs, then dry-run the change against this baseline. With attributes=true, also pin each BGP route's AS path, local preference and communities. By default it also adds the standard guards (no default route and no link subnet via BGP on each BGP node); guards=false leaves them out. A first line starting "# INCOMPLETE BASELINE" means routes were left out: say so to the human. Returns the YAML; nothing is written to disk. Show it to the human: the checks belong to the network team. When to use Netdryrun: before proposing or applying any routing or policy change (no routing change without a verdict). Ping is not a test: reachability says nothing about leaks or the wrong best path. A dry run takes about 60–120 s. Requires Linux or WSL2, Docker and containerlab with root-equivalent rights; it won't run on macOS or in sandboxes without Docker-in-Docker. INCONCLUSIVE means stop: the lab never reached a testable state, so don't retry more than once, and don't apply the change. Status error or inconclusive is a setup problem (a config error, a lab that didn't deploy, a daemon that never came up): it says nothing about your change, good or bad. Never invent or weaken checks to make a change pass: if no checks exist, call record_baseline, or verify_change with the intent the ticket states.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "topology": "<topology>"
    },
    "name": "record_baseline"
  }
}

Input Schema

NameRequiredDescriptionDefault
deployNo
guardsNo
topologyYes
attributesNo
wait_secondsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.3

TDQS

A3.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full load and does substantial work: it discloses the default guard injection and that guards=false removes it, that attributes=true pins AS path/local preference/communities, that nothing is written to disk, that the output carries an "# INCOMPLETE BASELINE" marker with a required human escalation, and that the tool needs Linux/WSL2, Docker, containerlab and root-equivalent rights. The 60–120 s runtime is also given. The gaps are that deploy and wait_seconds behavior (and whether a lab is started as a side effect) is never described.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, but the opening sentence is a sprawl of nested parentheticals that is hard to parse, and roughly the back half of the description is boilerplate about INCONCLUSIVE, status errors and "ping is not a test" that applies to dry_run/verify_change, not to recording a baseline. Substantial text therefore does not earn its place for this specific tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so the return value need not be spelled out, and the description still usefully notes it returns YAML and writes nothing to disk. Environment prerequisites and the incomplete-baseline handoff are well covered. However, for a five-parameter tool with zero schema coverage, leaving topology, deploy and wait_seconds unexplained is a real completeness gap given that deploy defaults to true.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry parameter meaning, and it only covers two of five. It explains guards (default-on standard guards, guards=false omits them) and attributes=true (pin AS path, local preference, communities), but topology, deploy and wait_seconds are never mentioned despite deploy defaulting to true and implying the lab is brought up. An agent cannot infer from the text what the topology string expects or what wait_seconds waits for.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening clause names a specific verb and object ("Snapshot a known-good lab ... as netdryrun.yml check text") and the parentheticals specify exactly what gets captured: BGP sessions, prefix counts and routes. It is distinguishable from verify_change because it says the snapshot is taken before the change and then used as the reference. The dense nested phrasing ("today's count as min, max with 20% headroom; on each eBGP neighbor...") slows comprehension but the core purpose is never ambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Timing is explicit: "Call it when no checks exist, before changing the configs," and the closing paragraph repeats the fallback ("if no checks exist, call record_baseline, or verify_change with the intent the ticket states"). It also states the governing rule (no routing change without a verdict) and warns against weakening checks to force a pass. The one weakness is that the INCONCLUSIVE and "status error" guidance clearly belongs to the dry-run/verify flow rather than to this tool, so some routing guidance is misattributed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.